Category Archives: Hockey

2019 NHL Draft Prospect Sentiment Analysis

Continuing our analysis of 2019 NHL Draft Prospects, this article looks at Scouting Reports and tweets on 2019 NHL Draft eligible prospects. In hopes of capturing some additional information outside of the numbers as seen by the “public” scouts. If you follow our NBA Draft content, you are already familiar with our sentiment analysis on 2019 NBA Draft Prospects. For those that are unaware, sentiment is a form of NLP (Natural Language Processing) or more formally defined as “the process of computationally identifying and categorizing opinions expressed in a piece of text, especially in order to determine whether the writer’s attitude towards a particular topic, product, etc., is positive, negative, or neutral.” Using Professor Bing Liu’s graded sentiment dictionary, we can analyze text to and identify who is more positively written about. For more information, please read our My Model Monday series article.

Continue reading 2019 NHL Draft Prospect Sentiment Analysis

2019 NHL Draft Role Probability Model

Our NHL Draft Role Probability Model uses prospects’ statistical production, physical measurements, league prominence, and team statistics to predict the likelihood that a players assume a specific NHL Role (i.e., First Line / Top Pair, Second Line / 2nd pair defensemen, 3rd Line / 3rd Pair, Fourth Line / 7th defensemen, Two-way player, and Non-NHL player). This Model expands on our NHL Translated PPG model in order to account for variables outside of Points Per Game, such as size, scouting ranks, caliber of leagues played in, etc. Continue reading 2019 NHL Draft Role Probability Model

2019 NHL Draft Prospects Translated PPG

This Friday, June 21st, 217 NHL prospects will be drafted with the hopes of becoming the next Sidney Crosby, Jamie Benn, or Evgeny Kuznetsov. Teams are faced with the difficult task of projecting young adults to the NHL, with some of those players coming from leagues that don’t even track second assists, and others coming from the highest levels of hockey. Analysts, Scouts, GMs, etc. will scour eliteprospects and hockeydb, checking out how many points a prospect produced in each league, and then try to use their small DB of memory to remember what NHL players also played in that league, and how they performed at the NHL level. Instead of using our 0.1 GB RAM human brains, we will use our 16GB RAM MacBook Pro to reference historical data necessary to translate point production across leagues for 2019 NHL Draft Eligible prospects.

Continue reading 2019 NHL Draft Prospects Translated PPG

A Non Model Based Minnesota Wild Season Preview

Okay Wild fans it’s that time of year. The time of year where we look at our roster, put on a brave face, and convince ourselves that this team can win a playoff series. Will it happen? Almost certainly not, but Marian Gaborik ain’t walking through that door any time soon, so we might as well reach deep into our hearts and minds and force ourselves to believe that we have enough talent up front to be a relevant NHL team in the 2018-2019 season. Is our top returning goal scorer turning 34 this month? Maybe he is, maybe he’s not. Age is just a number. Is the average age of our top two centers over 34? See above answer. Do we have almost exactly the same team we’ve had for the last six years? The team that has made it to the playoffs each of those last six years and won two playoff series? More or less, yes we do. None of this sounds good on paper, but as Minnesota Sports Fans it is our duty to ignore all signs of disaster and forge ahead with the most positive, if not delusional outlook we can manage. The general consensus amongst hockey pundits and fans is that the Wild will be one of, if not the, most boring team this year–and honestly, I don’t disagree. There is nothing about the Wild that screams “must watch.” Their best players aren’t exactly show stoppers. The closest things they have to gamebreakers are probably Zucker and Granlund and there are about 15 guys in the Central Division alone that I’d rather watch in a vacuum than those two. I don’t think anyone is paying top dollar to watch Koivu and Staal slow the game down (although Stubhub shows otherwise) and Suter might be the hardest top tier defensemen to watch in NHL history. It’s the same goddamn team they’ve trotted out for the last six years for christ’s sake. Sure those six years have all been playoff years but there is absolutely nothing about this team that should make anyone expect a legitimate playoff run this year. That being said, the Wild should be competitive in a very deep Central division. They don’t have the dynamic players that some of the top end teams have but they have a shit ton of depth at forward and defense and they’re experienced in terms of regular season success, so who the hell knows. They only thing I know for sure is that it’s going to be a long, long season, regardless of whether it ends after 82 games, or like 87 games… Continue reading A Non Model Based Minnesota Wild Season Preview

My Model Monday: Hockey Aging Curves

In this week’s My Model Monday, I explored aging curves in not just the NHL, but in other professional leagues and junior hockey leagues. First and foremost, what are aging curves? Aging curves are just what they sound like: curves that associate player performance and health over time. For a point of reference, despite his mighty accomplishments at an old age, Jaromir Jagr saw his point production dip from over a point per game at age 25 to about 0.3 PTS/G at age 45. Jaromir Jagr is an incredibly interesting case and likely outlier, as few players have played into their mid-forties. At any rate, one can imagine that many players experience similar increases and decreases in production with age; therefore, using many samples of players, one can construct a curve that resembles a mean of all players aging, or, as we like to say in the reinsurance industry, an industry exposure curve. Continue reading My Model Monday: Hockey Aging Curves

NHL Draft Model Results 2018 (Preliminary)

Below is results to our (preliminary) NHL Draft Model that uses prospects’ statistical production, physical measurements, and other variables to predict the likelihood that a players assume a specific NHL Role (i.e., First Line / Top Pair, Second / Third Line / 2nd pair defensemen, Fourth Line / Bottom pair defensemen, and Non-NHL player). The model is still being fine-tuned, hence the preliminary results, and an in-depth methodology article will come in the future. In addition to the aforementioned role probabilities, there is also a predicted NHL point per game that is derived from our Hockey Translation Factors.

Continue reading NHL Draft Model Results 2018 (Preliminary)

Model 284 Podcast: Hockey Translation Factors and Peter Lindblad Interview

In this episode of the Model 284 podcast, we catch you up on everything going on at Model 284, breakdown our Hockey League Translations Model, and interview professional hockey player Peter Lindblad to discuss analytics in hockey, professional hockey in Europe, Sunday punting, and more.

Hockey League Translation Factors: Methodology

I. Introduction

If you didn’t know, there are a lot of people in the world—7.6 billion to be exact! There are also a lot of people that play hockey. As a result, there are a lot of hockey leagues in the world. Wow. Okay, moving on… The National Hockey League (NHL) is seen as the premier hockey league in the world, but players don’t start their hockey career in the NHL, and most never make it to the NHL. Some would argue that it is possible to have a successful and prosperous hockey career even if you never play in the NHL. In this article, I attempt to quantify the differences between these leagues; more specifically, translating individual player production from one league to the next. This would allow us to say things such as Tony Cameranesi registered 50 points in 50 games, or 1.0 point per game, in the NCAA, thus you would expect him to produce xx amount in the AHL, yy amount in the KHL, zz amount in the NHL, etc.

Continue reading Hockey League Translation Factors: Methodology